Abstract: A raw byte sequence payload describing a picture in slices, WPP substreams or tiles and coded using context-adaptive binary arithmetic coding is subdivided into tranches with continuing the context-adaptive binary arithmetic coding probability adaptation across tranche boundaries. Thereby, tranche boundaries additionally introduced within slices, WPP substreams or tiles do not lead to a reduction in the entropy coding efficiency of these entities. However, the tranches are smaller than the original slices, WPP substreams or tiles and accordingly they may be transmitted earlier, i.e. with lower delay, than the un-chopped original entities. According to another aspect combinable with the first aspect, substream marker NAL units are used within a sequence of NAL units of a video bitstream to enable a transport demultiplexer to assign data of slices within NAL units to the corresponding substreams or tiles so as to be able to, in parallel, serve a multi-threaded decoder with the corresponding substreams or tiles.

Abstract: Disclosed herein are a method, an apparatus and a storage medium for image encoding/decoding using a palette mode. Prediction using a palette mode may be performed for a target block. Various types of predictions may be performed for the target block, and pieces of information to be signaled from an encoding apparatus to a decoding apparatus may be changed depending on the type of prediction to be performed for the target block. Determination of the pieces of information to be signaled may be optimized for the case where a palette mode is to be used for the target block, and thus efficiency of image encoding and decoding may be improved.

Abstract: A system and method of visual detection for a multi-sensor gateway using a stereo camera system. The system consists of two pillars and a stereo camera that build a gateway for patrons to pass through. Threat detection relies on artificial intelligence to analyze the sensors' data and assess the presence of a threat. The AI is performed on an edge device contained within the gateway. The gateway can consist of a number of peripherals that enhance the sensing capability of the gateway, such as a camera, or an accelerometer; or provide the security guard with information around alerts and threat locations such as with displays or audible alerts or manage the operations such as displays to control throughput.

Abstract: A three-dimensional data encoding method including: encoding tile information including information on N (N is an integer greater than or equal to 0) subspaces of a target space including three-dimensional points, and encoding point cloud data of the three-dimensional points based on the tile information; and generating a bitstream including the point cloud data encoded. The tile information includes N subspace coordinate information indicating coordinates of the N subspaces. The N subspace coordinate information each include three coordinate information each indicating a coordinate in one of three axial directions in a three-dimensional orthogonal coordinate system. When N is 1 or greater: in the encoding of the tile information, each of the three coordinate information is encoded using a first fixed length; and in the generating of the bitstream, the bitstream which includes the N subspace coordinate information encoded and first fixed length information indicating the first fixed length is generated.

Abstract: Apparatuses, systems, and techniques of identifying one or more distances to one or more objects. In at least one embodiment, one or more distances to one or more objects are identified based, at least in part on one or more first optical rays of a first image depicting an objects and one or more second optical rays a second images depicting the object. In at least one embodiment, one or more machine learning processes (e.g., neural network(s)) are used to identify a correspondence ray to determine distances to one or more objects.

Abstract: A method for encoding a three-dimensional (3D) point cloud into a bitstream, includes: obtaining octree information including an octree structure of a volume, wherein the octree structure includes a plurality of cuboids as leaf nodes of the octree structure; providing a threshold range; determining vertex positions Vj on edges of each cuboid as vertex information, wherein the vertex position Vj on the respective edge is determined by points of the point cloud in a distance to the respective edge smaller than the threshold range; and encoding the octree information and the vertex information into a bitstream; wherein the threshold range is dependent on the sizes of the cuboids.

Abstract: To enable better quality decoding of HDR images which are communicated as corresponding LDR images plus luma mapping functions, applicant teaches an encoder for encoding a high dynamic range image (Im_HDR_PSEU), which high dynamic range image is represented firstly by a matrix of pixel colors (Y_SDR, Cb_SDR, Cr_SDR) of an image of lower dynamic range (Im_SDR) than the high dynamic range image, which image of lower dynamic range gets compressed for communication as a compressed lower dynamic range image (Im_C), and also represented secondly by metadata (SEI) of the image which comprises a luma mapping function for calculating high dynamic range pixel lumas (Y_HDR) of the high dynamic range image by applying the function to pixel lumas of the image of lower dynamic range, wherein the encoder comprises an input (997) for receiving the luma mapping function (LMF) from an inverse tone mapping system (200), which is arranged to derive said luma mapping function based on analyzed properties of a master low dynamic r

Abstract: An imaging system receives depth data (corresponding to an environment) from a depth sensor and first image data (a depiction of the environment) from an image sensor. The imaging system generates, based on the depth data, first motion vectors corresponding to a change in perspective of the depiction of the environment in the first image data. The imaging system generates, using grid inversion based on the first motion vectors, second motion vectors that indicate respective distances moved by respective pixels of the depiction of the environment in the first image data for the change in perspective. The imaging system generates second image data by modifying the first image data according to the second motion vectors. The second image data includes a second depiction of the environment from a different perspective than the first image data. Some image reprojection applications (e.g., frame interpolation) can be performed without the depth data.

Abstract: In a method, a base mesh includes a subset of a plurality of vertices of a mesh. A position prediction of a current vertex of the base mesh is determined. A motion field prediction of the current vertex of the base mesh is determined. A position prediction residue for the position prediction of the current vertex is determined based on a first quantization step value. A motion field prediction residue for the motion field prediction of the current vertex is determined based on a second quantization step value, where the second quantization step value is dependent on the first quantization step value. A position of the current vertex of the base mesh is reconstructed based on the position prediction and the position prediction residue. A motion field of the current vertex of the base mesh is reconstructed based on the motion field prediction and the motion field prediction residue.

Abstract: Provided an image compression and transmission method and apparatus, an electronic device and a storage medium. An image to be processed is divided into a first area image located at a center of the image and a second area image surrounding an outer side of the first area image, and an inner contour of the second area image is adjacent to the first area image. The second area image is compressed based on compression information to generate a third area image, the compression information indicating a compression mode of the second area image, an inner contour of the third area image is adjacent to the first area image, and a resolution of the third area image is smaller than that of the second area image. A compressed image is generated based on the third area image, and the compressed image is sent to a display unit for displaying.

Abstract: A technique is described for improved issue reporting by a receiving device such as a set-top boxes for satellite and cable television services. In an example embodiment, the receiving device generates an issue report based on internal operational logs, captured screens and/or video of a visual output, and a recording of the user's voice that includes a description of the issue they are experiencing. This issue report can be generated as an object file that can then be transmitted, via a communications network, to an issue reporting platform for processing, for example, by a technical support representative or an automated troubleshooting system.

Abstract: This disclosure provides systems, methods, and devices for vehicle driving assistance systems that support image processing. In one aspect, a computing device determines a top-down view of an environment by determining corresponding frustums based on predicted depth information of pixels within image frames of the environment. Each frustum, associated with specific locations in the environment, may correspond to at least one pixel in the frames. The computing device may map vertically aligned frustums to the same location within a top-down representation. Other aspects and features are also claimed and described.

Abstract: The present disclosure relates to a method (100) for 3D reconstruction. The method comprises obtaining (S100) a set of images, each image overlapping a region of interest, performing (S400) image registration for the set of images, wherein performing the image registration comprises correlating (S410) each image with a reference 3D data set, the correlating (S410) of each image with the reference 3D data set being arranged to determine the positional accuracy of each image to the same positional accuracy of the reference 3D data set, and generating (S600) a 3D data set relating to the region of interest using (S610) 3D reconstruction based on the registered images. The present disclosure also relates to corresponding computer program products and systems.

Abstract: This disclosure provides systems, methods, and devices that support machine learning techniques for vehicle guidance. In one aspect, a method is provided that includes receiving an image frame from an image sensor, determining a projected image frame to correct a vertical axis of the image frame, and generating a top-down representation of the environment based on the projected image frame. The projected image frame may be aligned with the top down representation's vertical axis and may be projected using a cylindrical family projection. The top-down representation may be produced by assembling depth and context matrices from vertically aligned pixels in the projected image frame.

Abstract: Methods, apparatuses, and non-transitory computer-readable storage medium are provided for decoding video signals. A decoder receives a bitstream that includes a sequence parameter set (SPS) for video data. The decoder obtains arranged partition constraint syntax elements in sequence parameter set (SPS) level, and the arranged partition constraint syntax elements include intra prediction related syntax elements and inter prediction related syntax elements, and the arranged partition constraint syntax elements are arranged so that the intra prediction related syntax elements are defined before the inter prediction related syntax elements. The decoder decodes the video data based on the arranged partition constraint syntax elements.

Abstract: Embodiments herein relate to a process for electron holography image aberration reduction. A system can comprise a memory that stores, and a processor that executes, computer executable components. The computer executable components can comprise a propagating component that reduces hologram aberration of an electron hologram (EH) image by modifying of a pair of sequenced parameters of an array upon which the EH image is constructed, resulting in a modified array, and a generating component that generates a propagated EH image using a propagator comprising the modified array.

Abstract: Methods, apparatus, systems, and articles of manufacture to generate 3D point clouds based on spatiotemporal light patterns are disclosed. A controller includes processor circuitry to execute the instructions to generate a series of light patterns based on a set of light pattern tiles. Each of the light pattern tiles is defined by a different arrangement of illuminated pixels. Each of the light patterns is defined by a different arrangement of the light pattern tiles. The processor circuitry is to instruct a projector to project the series of light patterns; instruct an image sensor to capture a series of images of reflections of the series of light patterns; and generate a three-dimensional point cloud based on the series of captured images.

Abstract: An image encoding method for encoding an image includes generating a prediction image by a plurality of types of prediction image generating processing, the plurality of types of prediction image generating processing include an intra prediction, an inter prediction, and a synthesis prediction, wherein the synthesis prediction performs synthesis processing of synthesizing a prediction image of an inter prediction and a prediction image of an intra prediction to an encoding-target block, and encoding a difference between the prediction image generated and a pixel value of an image of the encoding-target block. The synthesis processing includes weighting processing performed to the prediction image of the inter prediction and the prediction image of the intra prediction. A weighting parameter of the prediction image of the intra prediction in the weighting processing is determined in accordance with a type of the intra prediction.

Abstract: An image encoding/decoding method and apparatus is provided. The image decoding method comprises determining at least one layer in an output layer set (OLS), and determining a number of sublayers for the at least one layer.

Abstract: Methods and apparatuses for processing of picture data or picture feature data using a neural network with two or more layers are provided. The present disclosure may be applied in the field of artificial intelligence (AI)-based video or picture compression technologies, and in particular, to the field of neural network-based video compression technologies. According to the present disclosure, position within the neural network, at which auxiliary information may be entered for processing is selectable based on a gathering condition. The gathering condition may assess whether some prerequisite is fulfilled. Advantages may include better performance in terms of rate and/or disclosure due to the effect of increased flexibility in neural network configurability.